Open Models Almanac
Methodsinference & servinginference quantization

single mention · inference & serving

Large-model quantization and speculative sampling

A broad compression toolset that includes quantization methods and speculative sampling, rather than one specific quantizer.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See inference quantization for the methods filed beside it.

Filed under inference & serving › inference quantization